© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17764
    Prev
    Next
    INDEX
    Explanations

    -centric, -focused, -driven, -oriented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ··
    -0.06
    ç»Ŀ
    -0.05
    æ¦ľ
    -0.05
    è¿ĩåįĬ
    -0.05
    积累
    -0.05
     longitudinal
    -0.05
    éŨåīį
    -0.05
    åįĬæķ°
    -0.05
    éļ¾
    -0.05
    ç´¯
    -0.05
    POSITIVE LOGITS
    slaught
    0.07
    åŀĭä¼ģä¸ļ
    0.07
    egov
    0.06
    ÙħاÛĮØ´
    0.06
    freund
    0.06
    erva
    0.06
    recken
    0.06
    ega
    0.06
    technolog
    0.06
    worthy
    0.06
    Activations Density 0.010%

    No Known Activations